{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"2007.13003","title":"Robust and Generalizable Visual Representation Learning via Random Convolutions","created":"2020-07-25","cited_by_count":142},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"1707.01629","title":"Dual Path Networks","created":"2017-07-06","cited_by_count":119},{"id":"2105.07197","title":"Are Convolutional Neural Networks or Transformers more like human vision?","created":"2021-05-15","cited_by_count":109},{"id":"2106.07617","title":"Delving Deep into the Generalization of Vision Transformers under Distribution Shifts","created":"2021-06-14","cited_by_count":85},{"id":"2010.05981","title":"Shape-Texture Debiased Neural Network Training","created":"2020-10-12","cited_by_count":76},{"id":"1905.09797","title":"Interpreting Adversarially Trained Convolutional Neural Networks","created":"2019-05-23","cited_by_count":75},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52},{"id":"2309.16779","title":"Intriguing properties of generative classifiers","created":"2023-09-28","cited_by_count":52},{"id":"2110.14189","title":"Robust Contrastive Learning Using Negative Samples with Diminished Semantics","created":"2021-10-27","cited_by_count":43},{"id":"2104.09789","title":"Does enhanced shape bias improve neural network robustness to common corruptions?","created":"2021-04-20","cited_by_count":32},{"id":"2403.09193","title":"Can We Talk Models Into Seeing the World Differently?","created":"2024-03-14","cited_by_count":23},{"id":"2006.09373","title":"The shape and simplicity biases of adversarially robust ImageNet-trained CNNs","created":"2020-06-16","cited_by_count":14},{"id":"2011.01901","title":"Learning Visual Representations for Transfer Learning by Suppressing Texture","created":"2020-11-03","cited_by_count":11},{"id":"2402.09530","title":"Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion","created":"2024-02-14","cited_by_count":11},{"id":"2401.09109","title":"Trapped in texture bias? A large scale comparison of deep instance segmentation","created":"2024-01-17","cited_by_count":10},{"id":"2409.15035","title":"Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP","created":"2024-09-23","cited_by_count":9},{"id":"2009.09827","title":"Radiologist-level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans","created":"2020-09-21","cited_by_count":8},{"id":"2009.11397","title":"Detection of Iterative Adversarial Attacks via Counter Attack","created":"2020-09-23","cited_by_count":4},{"id":"2407.21202","title":"Rolling in the deep of cognitive and AI biases","created":"2024-07-30","cited_by_count":2},{"id":"2211.13190","title":"BiasBed -- Rigorous Texture Bias Evaluation","created":"2022-11-23","cited_by_count":1},{"id":"2409.17109","title":"Unveiling Ontological Commitment in Multi-Modal Foundation Models","created":"2024-09-25","cited_by_count":1}],"next_cursor":null}